google-deepmind / google-deepmind/alphafold

Modifying a features.pkl file to crop/replace residues with a linker?

Open
#830 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
14.9k
Forks
2.9k
PR merge metrics
No merged PRs in 30d

Description

We want to replace specific residues in an existing features.pkl file with a (glycine) linker. For example, if a protein has 506 residues we would like to replace indexes 50 to 80 with glycine residues, so we can consider this part of the protein 'cropped out'.

Is there an existing method to replace certain indexes after a features.pkl file has already been created?

These are the tensors in the .pickle file that would have to be modified.
['aatype', 'all_atom_mask', 'all_atom_positions', 'asym_id', 'bert_mask', 'deletion_matrix', 'deletion_mean', 'entity_id',
'entity_mask', 'msa', 'msa_mask', 'residue_index', 'seq_mask', 'sym_id', 'template_aatype', 'template_all_atom_mask', 'template_all_atom_positions']

Any help is appreciated

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.